Top

European Journal of Nuclear Medicine and Molecular Imaging

Published in:

Open Access 21-11-2022 | Prostate Cancer | Original Article

Predicting clinically significant prostate cancer with a deep learning approach: a multicentre retrospective study

Authors: Litao Zhao, Jie Bao, Xiaomeng Qiao, Pengfei Jin, Yanting Ji, Zhenkai Li, Ji Zhang, Yueting Su, Libiao Ji, Junkang Shen, Yueyue Zhang, Lei Niu, Wanfang Xie, Chunhong Hu, Hailin Shen, Ximing Wang, Jiangang Liu, Jie Tian

Published in: European Journal of Nuclear Medicine and Molecular Imaging | Issue 3/2023

Abstract

Purpose

This study aimed to develop deep learning (DL) models based on multicentre biparametric magnetic resonance imaging (bpMRI) for the diagnosis of clinically significant prostate cancer (csPCa) and compare the performance of these models with that of the Prostate Imaging and Reporting and Data System (PI-RADS) assessment by expert radiologists based on multiparametric MRI (mpMRI).

Methods

We included 1861 consecutive male patients who underwent radical prostatectomy or biopsy at seven hospitals with mpMRI. These patients were divided into the training (1216 patients in three hospitals) and external validation cohorts (645 patients in four hospitals). PI-RADS assessment was performed by expert radiologists. We developed DL models for the classification between benign and malignant lesions (DL-BM) and that between csPCa and non-csPCa (DL-CS). An integrated model combining PI-RADS and the DL-CS model, abbreviated as PIDL-CS, was developed. The performances of the DL models and PIDL-CS were compared with that of PI-RADS.

Results

In each external validation cohort, the area under the receiver operating characteristic curve (AUC) values of the DL-BM and DL-CS models were not significantly different from that of PI-RADS (P > 0.05), whereas the AUC of PIDL-CS was superior to that of PI-RADS (P < 0.05), except for one external validation cohort (P > 0.05). The specificity of PIDL-CS for the detection of csPCa was much higher than that of PI-RADS (P < 0.05).

Conclusion

Our proposed DL models can be a potential non-invasive auxiliary tool for predicting csPCa. Furthermore, PIDL-CS greatly increased the specificity of csPCa detection compared with PI-RADS assessment by expert radiologists, greatly reducing unnecessary biopsies and helping radiologists achieve a precise diagnosis of csPCa.

Available only for authorised users

Sung H, Ferlay J, Siegel RL, Laversanne M, Soerjomataram I, Jemal A, et al. Global Cancer Statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2021;71:209–49. https://doi.org/10.3322/caac.21660.CrossRef

Weinreb JC, Barentsz JO, Choyke PL, Cornud F, Haider MA, Macura KJ, et al. PI-RADS prostate imaging - reporting and data system: 2015, Version 2. Eur Urol. 2016;69:16–40. https://doi.org/10.1016/j.eururo.2015.08.052.CrossRef

Kasivisvanathan V, Rannikko AS, Borghi M, Panebianco V, Mynderse LA, Vaarala MH, et al. MRI-targeted or standard biopsy for prostate-cancer diagnosis. N Engl J Med. 2018;378:1767–77. https://doi.org/10.1056/NEJMoa1801993.CrossRef

Barentsz JO, Richenberg J, Clements R, Choyke P, Verma S, Villeirs G, et al. ESUR prostate MR guidelines 2012. Eur Radiol. 2012;22:746–57. https://doi.org/10.1007/s00330-011-2377-y.CrossRef

Turkbey B, Rosenkrantz AB, Haider MA, Padhani AR, Villeirs G, Macura KJ, et al. Prostate imaging reporting and data system version 2.1: 2019 update of prostate imaging reporting and data system version 2. Eur Urol. 2019;76:340–51. https://doi.org/10.1016/j.eururo.2019.02.033.CrossRef

Kuhl CK, Bruhn R, Kramer N, Nebelung S, Heidenreich A, Schrading S. Abbreviated biparametric prostate MR imaging in men with elevated prostate-specific antigen. Radiology. 2017;285:493–505. https://doi.org/10.1148/radiol.2017170129.CrossRef

Kang Z, Min X, Weinreb J, Li Q, Feng Z, Wang L. Abbreviated biparametric versus standard multiparametric MRI for diagnosis of prostate cancer: a systematic review and meta-analysis. AJR Am J Roentgenol. 2019;212:357–65. https://doi.org/10.2214/AJR.18.20103.CrossRef

Tamada T, Kido A, Yamamoto A, Takeuchi M, Miyaji Y, Moriya T, et al. Comparison of biparametric and multiparametric MRI for clinically significant prostate cancer detection with PI-RADS Version 2.1. J Magn Reson Imaging. 2021;53:283–91. https://doi.org/10.1002/jmri.27283.CrossRef

Semelka RC, Ramalho M, AlObaidy M, Ramalho J. Gadolinium in humans: a family of disorders. AJR Am J Roentgenol. 2016;207:229–33. https://doi.org/10.2214/AJR.15.15842.CrossRef

10.

Chhor CM, Mercado CL. Abbreviated MRI protocols: wave of the future for breast cancer screening. AJR Am J Roentgenol. 2017;208:284–9. https://doi.org/10.2214/AJR.16.17205.CrossRef

11.

Wang Z, Liu C, Cheng D, Wang L, Yang X, Cheng KT. Automated detection of clinically significant prostate cancer in mp-MRI images based on an end-to-end deep neural network. IEEE Trans Med Imaging. 2018;37:1127–39. https://doi.org/10.1109/TMI.2017.2789181.CrossRef

12.

Cao R, Mohammadian Bajgiran A, Afshari Mirak S, Shakeri S, Zhong X, Enzmann D, et al. Joint prostate cancer detection and gleason score prediction in mp-MRI via FocalNet. IEEE Trans Med Imaging. 2019;38:2496–506. https://doi.org/10.1109/TMI.2019.2901928.CrossRef

13.

Schelb P, Kohl S, Radtke JP, Wiesenfarth M, Kickingereder P, Bickelhaupt S, et al. Classification of cancer at prostate MRI: deep learning versus clinical PI-RADS assessment. Radiology. 2019;293:607–17. https://doi.org/10.1148/radiol.2019190938.CrossRef

14.

Bonekamp D, Kohl S, Wiesenfarth M, Schelb P, Radtke JP, Gotz M, et al. Radiomic machine learning for characterization of prostate lesions with MRI: comparison to ADC values. Radiology. 2018;289:128–37. https://doi.org/10.1148/radiol.2018173064.CrossRef

15.

Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts H. Artificial intelligence in radiology. Nat Rev Cancer. 2018;18:500–10. https://doi.org/10.1038/s41568-018-0016-5.CrossRef

16.

Liu Z, Wang S, Dong D, Wei J, Fang C, Zhou X, et al. The applications of radiomics in precision diagnosis and treatment of oncology: opportunities and challenges. Theranostics. 2019;9:1303–22. https://doi.org/10.7150/thno.30309.CrossRef

17.

Shao L, Liu Z, Yan Y, Liu J, Ye X, Xia H, et al. Patient-level prediction of multi-classification task at prostate MRI based on end-to-end framework learning from diagnostic logic of radiologists. IEEE Trans Biomed Eng. 2021;68:3690–700. https://doi.org/10.1109/TBME.2021.3082176.CrossRef

18.

Shao L, Yan Y, Liu Z, Ye X, Xia H, Zhu X, et al. Radiologist-like artificial intelligence for grade group prediction of radical prostatectomy for reducing upgrading and downgrading from biopsy. Theranostics. 2020;10:10200–12. https://doi.org/10.7150/thno.48706.CrossRef

19.

Yan Y, Shao L, Liu Z, He W, Yang G, Liu J, et al. Deep learning with quantitative features of magnetic resonance images to predict biochemical recurrence of radical prostatectomy: a multi-center study. Cancers. 2021;13:3098. https://doi.org/10.3390/cancers13123098.CrossRef

20.

Netzer N, Weisser C, Schelb P, Wang X, Qin X, Gortz M, et al. Fully automatic deep learning in bi-institutional prostate magnetic resonance imaging: effects of cohort size and heterogeneity. Invest Radiol. 2021. https://doi.org/10.1097/RLI.0000000000000791.CrossRef

21.

Hatt M, Tixier F, Pierce L, Kinahan PE, Le Rest CC, Visvikis D. Characterization of PET/CT images using texture analysis: the past, the present... any future? Eur J Nucl Med Mol Imaging. 2017;44:151–65. https://doi.org/10.1007/s00259-016-3427-0.CrossRef

22.

O’Connor JP, Aboagye EO, Adams JE, Aerts HJ, Barrington SF, Beer AJ, et al. Imaging biomarker roadmap for cancer studies. Nat Rev Clin Oncol. 2017;14:169–86. https://doi.org/10.1038/nrclinonc.2016.162.CrossRef

23.

Papadimitroulas P, Brocki L, Christopher Chung N, Marchadour W, Vermet F, Gaubert L, et al. Artificial intelligence: deep learning in oncological radiomics and challenges of interpretability and data harmonization. Phys Med. 2021;83:108–21. https://doi.org/10.1016/j.ejmp.2021.03.009.CrossRef

24.

He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016. pp 770–8.

25.

Huang G, Liu Z, Maaten LVD, Weinberger KQ. Densely connected convolutional networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2017. pp 2261–9.

26.

Zhang X, Zhou X, Lin M, Sun J. ShuffleNet: an extremely efficient convolutional neural network for mobile devices. IEEE/CVF Conference on Computer Vision and Pattern Recognition; 2018. p. 6848–56.

27.

Andrew GH, Zhu M, Chen B, et al. MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv; 2017;1–10. https://doi.org/10.48550/arXiv.1704.04861.

28.

Saha A, Hosseinzadeh M, Huisman H. End-to-end prostate cancer detection in bpMRI via 3D CNNs: effects of attention mechanisms, clinical priori and decoupled false positive reduction. Med Image Anal. 2021;73:102155. https://doi.org/10.1016/j.media.2021.102155.CrossRef

29.

Edward S, Sandy S, Emmanuel SA, et al. NCCN clinical practice guidelines in oncology, Prostate Cancer version 1. 2022. NCCN. 2022. https://www.nccn.org/professionals/physician_gls/pdf/prostate.pdf.

30.

Stark JR, Perner S, Stampfer MJ, Sinnott JA, Finn S, Eisenstein AS, et al. Gleason score and lethal prostate cancer: does 3 + 4 = 4 + 3? J Clin Oncol. 2009;27:3459–64. https://doi.org/10.1200/JCO.2008.20.4669.CrossRef

31.

Ahmed HU, El-Shater Bosaily A, Brown LC, Gabe R, Kaplan R, Parmar MK, et al. Diagnostic accuracy of multi-parametric MRI and TRUS biopsy in prostate cancer (PROMIS): a paired validating confirmatory study. The Lancet. 2017;389:815–22. https://doi.org/10.1016/s0140-6736(16)32401-1.CrossRef

32.

Yang X, Liu C, Wang Z, Yang J, Min HL, Wang L, et al. Co-trained convolutional neural networks for automated detection of prostate cancer in multi-parametric MRI. Med Image Anal. 2017;42:212–27. https://doi.org/10.1016/j.media.2017.08.006.CrossRef

33.

Wu M, Krishna S, Thornhill RE, Flood TA, McInnes MDF, Schieda N. Transition zone prostate cancer: logistic regression and machine-learning models of quantitative ADC, shape and texture features are highly accurate for diagnosis. J Magn Reson Imaging. 2019;50:940–50. https://doi.org/10.1002/jmri.26674.CrossRef

34.

Chen T, Li M, Gu Y, Zhang Y, Yang S, Wei C, et al. Prostate cancer differentiation and aggressiveness: assessment with a radiomic-based model vs PI-RADS v2. J Magn Reson Imaging. 2019;49:875–84. https://doi.org/10.1002/jmri.26243.CrossRef

35.

Yi Z, Hu S, Lin X, Zou Q, Zou M, Zhang Z, et al. Machine learning-based prediction of invisible intraprostatic prostate cancer lesions on (68) Ga-PSMA-11 PET/CT in patients with primary prostate cancer. Eur J Nucl Med Mol Imaging. 2022;49:1523–34. https://doi.org/10.1007/s00259-021-05631-6.CrossRef

36.

Zamboglou C, Carles M, Fechter T, Kiefer S, Reichel K, Fassbender TF, et al. Radiomic features from PSMA PET for non-invasive intraprostatic tumor discrimination and characterization in patients with intermediate- and high-risk prostate cancer - a comparison study with histology reference. Theranostics. 2019;9:2595–605. https://doi.org/10.7150/thno.32376.CrossRef

37.

Zamboglou C, Bettermann AS, Gratzke C, Mix M, Ruf J, Kiefer S, et al. Uncovering the invisible-prevalence, characteristics, and radiomics feature-based detection of visually undetectable intraprostatic tumor lesions in (68)GaPSMA-11 PET images of patients with primary prostate cancer. Eur J Nucl Med Mol Imaging. 2021;48:1987–97. https://doi.org/10.1007/s00259-020-05111-3.CrossRef

38.

Alongi P, Stefano A, Comelli A, Laudicella R, Scalisi S, Arnone G, et al. Radiomics analysis of 18F-Choline PET/CT in the prediction of disease outcome in high-risk prostate cancer: an explorative study on machine learning feature classification in 94 patients. Eur Radiol. 2021;31:4595–605. https://doi.org/10.1007/s00330-020-07617-8.CrossRef

Title: Predicting clinically significant prostate cancer with a deep learning approach: a multicentre retrospective study
Authors: Litao Zhao
Jie Bao
Xiaomeng Qiao
Pengfei Jin
Yanting Ji
Zhenkai Li
Ji Zhang
Yueting Su
Libiao Ji
Junkang Shen
Yueyue Zhang
Lei Niu
Wanfang Xie
Chunhong Hu
Hailin Shen
Ximing Wang
Jiangang Liu
Jie Tian
Publication date: 21-11-2022
Publisher: Springer Berlin Heidelberg
Keywords: Prostate Cancer
Magnetic Resonance Imaging
Magnetic Resonance Imaging
Prostate Cancer
Published in: European Journal of Nuclear Medicine and Molecular Imaging / Issue 3/2023
Print ISSN: 1619-7070
Electronic ISSN: 1619-7089
DOI: https://doi.org/10.1007/s00259-022-06036-9

At a glance: The STEP trials

Springer Medicine

Predicting clinically significant prostate cancer with a deep learning approach: a multicentre retrospective study

Abstract

Purpose

Methods

Results

Conclusion

At a glance: The STEP trials

Springer Medicine

Abstract

Purpose

Methods

Results

Conclusion

Please log in to get access to this content

Other articles of this Issue 3/2023

Correction to: Nuclear medicine in the assessment and prevention of cancer therapy‑related cardiotoxicity: prospects and proposal of use by the European Association of Nuclear Medicine (EANM)

Preliminary efficacy of [90Y]DOTA-biotin-avidin radiotherapy against non-muscle invasive bladder cancer

PET molecular imaging for pathophysiological visualization in Alzheimer’s disease

Authors’ reply to Dr. Paolo Duarte: Combined [68Ga]Ga-PSMA-11 and low-dose [18F]FDG PET/CT using a long-axial field of view scanner for patients referred for [177Lu]-PSMA-radioligand therapy

Cross-reactivity to glutamate carboxypeptidase III causes undesired salivary gland and kidney uptake of PSMA-targeted small-molecule radionuclide therapeutics

Predicting pathological highly invasive lung cancer from preoperative [18F]FDG PET/CT with multiple machine learning models